Abstract (EN)

The tutorial aims at introducing the general field that deals with techniques for representing, learning and reasoning with preferences. While the community of Recommender Systems has recently done extensive work in techniques for providing user recommendations in different settings, preferences have been formally studied since several decades (the community that studies preferences from a formal algorithmic point of view is now often called algorithmic decision theory). Preferences are a basic concept for several research fields such as economics, decision theory, game theory, artificial intelligence, classification, data bases, etc.; preferences constitute a key concept for the development of recommender systems since they represent the elementary information upon which recommendations are constructed. The tutorial will introduce both the formalisms more widely used to model and represent preferences as well as the procedures aimed at learning preferences and at producing a recommendation for an end-user (decision maker).